Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code and documentation artifacts such as comments, properties, and namespaces

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.69
    -0.59
    esModule
    -0.52
     يتيمه
    -0.50
    +:+
    -0.49
    AnchorStyles
    -0.49
    RunWith
    -0.48
    الإنجليزية
    -0.47
    __*/
    -0.47
    +#+#
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیا
    0.42
     emancipation
    0.37
     perpetuity
    0.37
     Esco
    0.36
    productions
    0.36
    [toxicity=0]
    0.35
     aceton
    0.35
    uests
    0.34
     coch
    0.34
     allegro
    0.34
    Act Density 3.942%

    No Known Activations